[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <d5247a6c-2088-cbfa-20f9-c1c748f90daf@linux.ibm.com>
Date: Thu, 20 Jan 2022 11:27:43 +0100
From: Christian Borntraeger <borntraeger@...ux.ibm.com>
To: Janosch Frank <frankja@...ux.ibm.com>,
Janis Schoetterl-Glausch <scgl@...ux.ibm.com>,
Heiko Carstens <hca@...ux.ibm.com>,
Vasily Gorbik <gor@...ux.ibm.com>,
Alexander Gordeev <agordeev@...ux.ibm.com>,
David Hildenbrand <david@...hat.com>
Cc: Claudio Imbrenda <imbrenda@...ux.ibm.com>,
linux-s390@...r.kernel.org, linux-kernel@...r.kernel.org,
kvm@...r.kernel.org
Subject: Re: [RFC PATCH v1 02/10] KVM: s390: Honor storage keys when accessing
guest memory
Am 18.01.22 um 15:38 schrieb Janosch Frank:
[...]
> /*
> We'll do an actual access via the mv instruction which will return access errors to us so we don't need to check here.
> */
Be slightly more verbose I guess. Something like
We'll do an actual access via the mv instruction which will return access errors to us so we don't need to check here.
By using key 0 all checks are skipped and no performance overhead occurs.
?
>> + rc = guest_range_to_gpas(vcpu, ga, ar, gpas, len, asce, mode, 0);
Powered by blists - more mailing lists